Speech Emotion Classification using Ensemble Models with MFCC

Speech is one of the most promising features that reflects the underlying emotion of a human being. There are some measurable parameters in speech signals that reveal a persons affective state. Speech Emotion Recognition (SER) is a process of identifying the emotional elements in communication regardless of contextual relevance. Leveraging studies have taken place in this area. This paper proposes an ensemble model to automatically classify emotion from speech signals to one among the seven emotional classes neutral, calm, angry, sad, happy, fear, disgust, and surprised. In this work, speech spectral features have been extracted using Mel Frequency Cepstral Coefficient (MFCC). An emotion classification model based on 2-Dimensional Convolutional Neural Networks (2D-CNN) and eXtreme Gradient Boosting (XG-Boost) is proposed in this paper. This work also compares the performance of the proposed ensemble model with baseline models and other ensemble models. The accuracy of each model on the Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS) dataset is computed and the proposed model shows maximum accuracy in classifying emotions.